EmptyDroplets (FDR <= 0.1) + scDblFindersetwd("/media/jacopo/Elements/re_align/MM/PRJNA732205/SAMN19314101/SRR14629343/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)
Load and do the QC for the cellranger data
#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial,
"\nNumber of genes:", dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 3474
## Number of genes: 36601
Empty cells were already filtered, check for % mt RNA and death markers:
# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 15
max_counts = 30000
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt")) + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1
plot2
## cells retained by mt RNA content ( 15 %): 3212
## percentage of retained cells: 92.46 %
## cells retained by counts ( 30000 ): 3208
## percentage of retained cells: 92.34 %
Check the distribution of the cells with low counts and control death markers:
min_counts = 350
hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")
hist(dat@meta.data$nCount_RNA, breaks = 1000, xlab = "Counts", xlim = c(0,5000))
hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)
The evident peak of cells with < 200 counts could contain dying
cells.
# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)
# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)
# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)
# Print the most highly expressed genes
head(meanCounts, 30)
## IGKC IGHG4 MALAT1 B2M RPLP1 RPS18 RPL10
## 67.4994536 9.2524590 7.6480874 3.1967213 2.0644809 1.9693989 1.8043716
## SSR4 RPS14 RPL41 RPL32 RPL35 RPS27 RPL13
## 1.5431694 1.3081967 1.1934426 1.1344262 1.1213115 1.0743169 1.0524590
## RPL34 RPS19 RPL13A MZB1 RPL35A RPS6 RPLP2
## 0.9989071 0.9868852 0.9770492 0.9748634 0.9300546 0.9278689 0.8852459
## RPS17 RPL27A RPS15 EEF1A1 RPL26 RPL17 RPS23
## 0.8284153 0.8207650 0.8163934 0.8142077 0.7857923 0.7803279 0.7781421
## RPL18A FTL
## 0.7770492 0.7748634
## cells retained by counts ( 350 ): 2292
## percentage of retained cells: 65.98 %
dir.create("result")
saveRDS(dat, file = "./result/SAMN19314101_clean_QC.Rds")
#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)
Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering
# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data
all.genes <- rownames(dat)
dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))
dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1
## Positive: RPS18, RPL10, RPS8, RPS20, RPL32
## Negative: HBA1, HBA2, HBB, ALAS2, HBM
## PC_ 2
## Positive: RPS18, RPS27, RPL13, RPL32, RPS12
## Negative: LMAN2, HLA-B, HLA-DOB, PDIA6, B2M
## PC_ 3
## Positive: HBA1, HBA2, HBB, RPL10, RPLP1
## Negative: PPP1R15A, IER2, JUN, HIST1H2BG, IER3
## PC_ 4
## Positive: MZB1, ITM2C, IGHG2, CYBA, SSR4
## Negative: HBA1, HBB, HBA2, STMN1, PCLAF
## PC_ 5
## Positive: IGHG2, IGHV1-24, PCLAF, DDX17, ODC1
## Negative: B2M, Z93241.1, NFKBIA, AL021155.5, HIST1H2BG
UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:
dat <- FindNeighbors(dat, dims = 1:20)
The graph now can be used as input for the function
runUMAP()
dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)
## QC metrics
## markers